Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Detect delimiter in CSV rendering #7869

Merged
merged 11 commits into from
Aug 15, 2019
61 changes: 58 additions & 3 deletions modules/markup/csv/csv.go
Original file line number Diff line number Diff line change
Expand Up @@ -9,12 +9,18 @@ import (
"encoding/csv"
"html"
"io"
"regexp"
"strings"

"code.gitea.io/gitea/modules/markup"
"code.gitea.io/gitea/modules/util"
)

var quoteRegexp = regexp.MustCompile(`["'][\s\S]+?["']`)

func init() {
markup.RegisterParser(Parser{})

}

// Parser implements markup.Parser for orgmode
Expand All @@ -28,12 +34,13 @@ func (Parser) Name() string {

// Extensions implements markup.Parser
func (Parser) Extensions() []string {
return []string{".csv"}
return []string{".csv", ".tsv"}
}

// Render implements markup.Parser
func (Parser) Render(rawBytes []byte, urlPrefix string, metas map[string]string, isWiki bool) []byte {
func (p Parser) Render(rawBytes []byte, urlPrefix string, metas map[string]string, isWiki bool) []byte {
rd := csv.NewReader(bytes.NewReader(rawBytes))
rd.Comma = p.bestDelimiter(rawBytes)
var tmpBlock bytes.Buffer
tmpBlock.WriteString(`<table class="table">`)
for {
Expand All @@ -50,9 +57,57 @@ func (Parser) Render(rawBytes []byte, urlPrefix string, metas map[string]string,
tmpBlock.WriteString(html.EscapeString(field))
tmpBlock.WriteString("</td>")
}
tmpBlock.WriteString("<tr>")
tmpBlock.WriteString("</tr>")
}
tmpBlock.WriteString("</table>")

return tmpBlock.Bytes()
}

// bestDelimiter scores the input CSV data against delimiters, and returns the best match.
// Reads at most 10k bytes & 10 lines.
func (p Parser) bestDelimiter(data []byte) rune {
maxLines := 10
maxBytes := util.Min(len(data), 1e4)
text := string(data[:maxBytes])
text = quoteRegexp.ReplaceAllLiteralString(text, "")
lines := strings.SplitN(text, "\n", maxLines+1)
lines = lines[:util.Min(maxLines, len(lines))]

delimiters := []rune{',', ';', '\t', '|'}
bestDelim := delimiters[0]
bestScore := 0.0
for _, delim := range delimiters {
score := p.scoreDelimiter(lines, delim)
if score > bestScore {
bestScore = score
bestDelim = delim
}
}

return bestDelim
}

// scoreDelimiter uses a count & regularity metric to evaluate a delimiter against lines of CSV
func (Parser) scoreDelimiter(lines []string, delim rune) (score float64) {
countTotal := 0
countLineMax := 0
linesNotEqual := 0

for _, line := range lines {
if len(line) == 0 {
continue
}

countLine := strings.Count(line, string(delim))
countTotal += countLine
if countLine != countLineMax {
if countLineMax != 0 {
linesNotEqual++
}
countLineMax = util.Max(countLine, countLineMax)
}
}

return float64(countTotal) * (1 - float64(linesNotEqual)/float64(len(lines)))
}
11 changes: 8 additions & 3 deletions modules/markup/csv/csv_test.go
Original file line number Diff line number Diff line change
Expand Up @@ -13,9 +13,14 @@ import (
func TestRenderCSV(t *testing.T) {
var parser Parser
var kases = map[string]string{
"a": "<table class=\"table\"><tr><td>a</td><tr></table>",
"1,2": "<table class=\"table\"><tr><td>1</td><td>2</td><tr></table>",
"<br/>": "<table class=\"table\"><tr><td>&lt;br/&gt;</td><tr></table>",
"a": "<table class=\"table\"><tr><td>a</td></tr></table>",
"1,2": "<table class=\"table\"><tr><td>1</td><td>2</td></tr></table>",
"1;2": "<table class=\"table\"><tr><td>1</td><td>2</td></tr></table>",
"1\t2": "<table class=\"table\"><tr><td>1</td><td>2</td></tr></table>",
"1|2": "<table class=\"table\"><tr><td>1</td><td>2</td></tr></table>",
"1,2,3;4,5,6;7,8,9\na;b;c": "<table class=\"table\"><tr><td>1,2,3</td><td>4,5,6</td><td>7,8,9</td></tr><tr><td>a</td><td>b</td><td>c</td></tr></table>",
"\"1,2,3,4\";\"a\nb\"\nc;d": "<table class=\"table\"><tr><td>1,2,3,4</td><td>a\nb</td></tr><tr><td>c</td><td>d</td></tr></table>",
"<br/>": "<table class=\"table\"><tr><td>&lt;br/&gt;</td></tr></table>",
}

for k, v := range kases {
Expand Down
1 change: 1 addition & 0 deletions public/css/index.css
Original file line number Diff line number Diff line change
Expand Up @@ -489,6 +489,7 @@ footer .ui.left,footer .ui.right{line-height:40px}
.repository.file.list .non-diff-file-content .view-raw img{padding:5px 5px 0 5px}
.repository.file.list .non-diff-file-content .plain-text{padding:1em 2em 1em 2em}
.repository.file.list .non-diff-file-content .plain-text pre{word-break:break-word;white-space:pre-wrap}
.repository.file.list .non-diff-file-content .csv{overflow-x:auto}
.repository.file.list .non-diff-file-content pre{overflow:auto}
.repository.file.list .sidebar{padding-left:0}
.repository.file.list .sidebar .octicon{width:16px}
Expand Down
4 changes: 4 additions & 0 deletions public/less/_repository.less
Original file line number Diff line number Diff line change
Expand Up @@ -400,6 +400,10 @@
}
}

.csv {
overflow-x: auto;
}

pre {
overflow: auto;
}
Expand Down
6 changes: 4 additions & 2 deletions routers/repo/view.go
Original file line number Diff line number Diff line change
Expand Up @@ -162,8 +162,9 @@ func renderDirectory(ctx *context.Context, treeLink string) {
d, _ := ioutil.ReadAll(dataRc)
buf = charset.ToUTF8WithFallback(append(buf, d...))

if markup.Type(readmeFile.Name()) != "" {
if markupType := markup.Type(readmeFile.Name()); markupType != "" {
ctx.Data["IsMarkup"] = true
ctx.Data["MarkupType"] = string(markupType)
ctx.Data["FileContent"] = string(markup.Render(readmeFile.Name(), buf, treeLink, ctx.Repo.Repository.ComposeMetas()))
} else {
ctx.Data["IsRenderedHTML"] = true
Expand Down Expand Up @@ -282,8 +283,9 @@ func renderFile(ctx *context.Context, entry *git.TreeEntry, treeLink, rawLink st

readmeExist := markup.IsReadmeFile(blob.Name())
ctx.Data["ReadmeExist"] = readmeExist
if markup.Type(blob.Name()) != "" {
if markupType := markup.Type(blob.Name()); markupType != "" {
ctx.Data["IsMarkup"] = true
ctx.Data["MarkupType"] = markupType
ctx.Data["FileContent"] = string(markup.Render(blob.Name(), buf, path.Dir(treeLink), ctx.Repo.Repository.ComposeMetas()))
} else if readmeExist {
ctx.Data["IsRenderedHTML"] = true
Expand Down
2 changes: 1 addition & 1 deletion templates/repo/view_file.tmpl
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,7 @@
</div>
</h4>
<div class="ui attached table unstackable segment">
<div class="file-view {{if .IsMarkup}}markdown{{else if .IsRenderedHTML}}plain-text{{else if .IsTextFile}}code-view{{end}} has-emoji">
<div class="file-view {{if .IsMarkup}}{{.MarkupType}}{{else if .IsRenderedHTML}}plain-text{{else if .IsTextFile}}code-view{{end}} has-emoji">
{{if .IsMarkup}}
{{if .FileContent}}{{.FileContent | Safe}}{{end}}
{{else if .IsRenderedHTML}}
Expand Down